© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 97848
    Prev
    Next
    INDEX
    Explanations

    PH

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dfunding
    -0.10
    D
    -0.10
    tei
    -0.09
    acious
    -0.09
    iasis
    -0.09
    alogy
    -0.09
    TE
    -0.09
    atively
    -0.09
    atics
    -0.09
    orne
    -0.09
    POSITIVE LOGITS
    PMailer
    0.17
    YSICAL
    0.14
    OTOS
    0.12
    ANT
    0.10
    Ầ
    0.09
    ASE
    0.09
    Ả
    0.08
    ONES
    0.08
    IDAY
    0.08
     Voz
    0.08
    Activations Density 0.002%

    No Known Activations